stoneforge AGENTS.md

Repository instructions for Stoneforge, a software project with backend services, shared packages, command-line tools, APIs, and documentation managed through its own commands.

In plain words
What is it for?
Adding API endpoints or core types, changing dependency or orchestration services, using the command line and APIs, and customizing prompts for coding agents.
Why use it?
They provide a map from common development tasks to the relevant files and reference documents, so developers can find the right implementation and guidance quickly.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/stoneforge-ai/stoneforge/agents-md
Clone the repo
git clone --depth 1 https://github.com/stoneforge-ai/stoneforge

Made for: Codex, OpenCode.

Per session 2,928 This file is loaded in full into every session.
When invoked 2,928 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02928 $0.02928
Opus 5 $0.01464 $0.01464
Sonnet 5 $0.00586 $0.00586
Haiku 4.5 $0.00293 $0.00293

Measured 2d ago against content hash 617caa46df00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stoneforge AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Context and instructions for AI coding agents working on the Stoneforge repository.

How to Find Documentation

  1. This file — Quick task-to-file mappings below
  2. Documentation Directory — Full index of all workspace docs: sf show el-30yb
  3. Category Index — Browse by category: sf show el-og6v
  4. Full-text search — Find any doc by topic: sf document search "your topic"

Quick Start

Backend Tasks

I need... Key Files Reference Doc
Add an API endpoint apps/quarry-server/src/index.ts, apps/smithy-server/src/routes/ sf show el-5z1q
Add a core type packages/core/src/types/ sf show el-6c3s
Work with dependencies packages/quarry/src/services/dependency.ts sf show el-200z
Add an orchestrator service packages/smithy/src/services/ sf show el-50ia
Use the CLI packages/quarry/src/cli/commands/ sf show el-59tr
Use the QuarryAPI packages/quarry/src/api/quarry-api.ts sf show el-kflh
Use the OrchestratorAPI packages/smithy/src/api/orchestrator-api.ts sf show el-3qg2
Customize agent prompts .stoneforge/prompts/ sf show el-32rb
Configure identity packages/quarry/src/systems/identity.ts sf show el-2jw5
Understand event sourcing packages/core/src/types/event.ts sf show el-58k3
Configure the system packages/quarry/src/config/ sf show el-z1sj

Frontend Tasks

I need... Key Files Reference Doc
Modify a smithy-web page apps/smithy-web/src/routes/{page}/ sf show el-4b3q
Modify a quarry-web page apps/quarry-web/src/routes/{page}/ sf show el-4iiz
Add a new frontend route apps/{app}/src/router.tsx sf show el-232d
Modify shared UI components packages/ui/src/ sf show el-2hk5
Add a React component apps/{app}/src/components/ sf show el-3gg7
Work with API hooks (smithy) apps/smithy-web/src/api/hooks/ sf show el-4b3q
Work with API hooks (quarry) apps/quarry-web/src/api/hooks/ sf show el-4iiz
Understand frontend architecture sf show el-935d

Read the full file on GitHub · 263 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 263 lines · 2,928 tokens per session scan A 617caa46df00

Subscribe to this mod's changes

stoneforge AGENTS.md is an instructions file published in the GitHub repository stoneforge-ai/stoneforge (177 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 2,928 tokens to every session, about $0.0146 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.